Latest · 最新
Oct 27, 2026
Three papers grade the harness, and model scale doesn't save you
For two years agent evals scored the model and treated the harness as plumbing. Three papers in Monday's arXiv batch score the plumbing, and the plumbing turns out to decide a lot.…
Oct 26, 2026
Pomerado turns websites into MCP tools instead of browsing them
Pomerado launched on YC on Sunday with a one-line pitch: "Pomerado turns any website into an API / MCP, in minutes." It is in the YC Fall 2026 batch, and the core is open source un…
Oct 26, 2026
AgentGrid.io gives each agent its own folder permissions
AgentGrid.io was the number two launch on Product Hunt on Sunday, and it's a cleaner idea than most of what ships in the "workspace for agents" category. The pitch: "The shared dri…
Oct 25, 2026
Claude MCP Tasks: overnight jobs arrive, and so does the double-refund problem
Anthropic added support for MCP Tasks and Elicitations in Claude on Friday evening. Tasks let Claude hand a plugin a long-running job, such as deep research, and get a report back …
Oct 22, 2026
Claude Duet and Walmart shipped on the same day, and both are really selling the permission slip
Anthropic launched Claude Duet on October 21, a standalone app where Claude works as a proactive agent instead of a chat box. It runs on Opus 5.5, has its own virtual machine with …
Oct 17, 2026
OpenCode 2.0: one daemon behind every surface, and every MCP server becomes a function the agent scripts
OpenCode 2.0 went to Hacker News on October 14 and sat at 848 points with 370 comments, two days after the project's own launch post passed 719,000 impressions. The repo is at 214,…
Oct 14, 2026
DishwasherBench: the verifier is a physics engine and a real Bosch
Can a frontier model stack a dishwasher? Composo built a benchmark where the answer is settled by physics rather than a rubric. DishwasherBench models one real machine, a Bosch SMV…
Oct 13, 2026
Agents Grep by Habit. Pensieve Says One Search Beats Forty Reads, and a Microsoft Paper Says That Is the Whole Problem.
Pensieve is a free, MIT-licensed Mac app from Ted Haley that indexes your files, repos and coding-agent sessions locally and exposes one search over MCP, so an agent asks a questio…
Oct 10, 2026
Sierra Published Poppy, the Spec for Agents Doing Business With Companies. 37 Partners, Apache 2.0.
Three days after announcing it, Sierra put the draft on the table. Personal Agent Protocol, which everyone involved calls Poppy, is now a readable Draft 0.1 at personalagentprotoco…
Oct 9, 2026
Google's Gemini Agent Gets Its Own Email Address and Picks Claude When It Wants To
At Gemini at Work on Thursday, Google Cloud CEO Thomas Kurian announced "the Gemini agent," a single agent for work that answers questions, does knowledge work, makes media and wri…
Page 1
Older →
Hiring · 招聘
New positions at AI agent companies, tracked as they open.
Vercel
Strategy and Planning Lead
Vercel
Sales Strategy & Operations, Enterprise
Glean
Office Manager
Glean
Design Engineer
Isomorphic Labs
Research Lead (Formulation Sciences), London
xAI
Sr. Manager, Materials Management - Memphis